Objective To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT). Design A diagnostic accuracy study. Setting A single-centre study. Participants A total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes. Main outcome measures The diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map). Results Deep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage. Conclusions Deep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice. Clinical trial registration number 000034587.

Purpose: To assess the effect of aging on corneal biomechanical parameters in a normal population. Methods: We prospectively examined 204 normal eyes of 204 healthy Japanese volunteers (68 men, 136 women; mean age 46.7±19.4 years [range: 19 to 89 years]). Corneal hysteresis, corneal resistance factor, corneal-compensated intraocular pressure (IOP _cc ), and Goldmann-correlated intraocular pressure (IOP _G ) were qualitatively assessed using a Reichert Ocular Response Analyzer. Central corneal thickness was measured using an ultrasound pachymeter. This measurement was performed 3 times, and the mean value obtained was used for statistical analysis. The relationships between patient age and corneal biomechanical parameters, or age and intraocular pressure (IOP), were investigated. Results: Mean corneal hysteresis and corneal resistance factor were 10.1±1.5 mmHg and 10.1±1.6 mmHg, respectively. Mean central corneal thickness was 539.1±30.9 µm. A weak, but significant, negative correlation was found between age and corneal hysteresis (Pearson's correlation coefficient r=−0.17, P =.02) and corneal resistance factor (r=−0.18 P =.01). On the other hand, no significant correlation was found between age and central corneal thickness (r=−0.06, P =.41), age and IOP _cc (r=−0.02, P =.82), or age and IOP _G (r=−0.11, P =.11). Conclusions: Corneal biomechanical parameters are significantly decreased by aging without significant changes in central corneal thickness or IOP, suggesting that age-related structural changes resulting from collagen cross-linking may lead to a reduction of corneal biomechanical variables independent of central corneal thickness or IOP. [ J Refract Surg . 2009;25:888–893.]

To assess the long-term clinical outcomes of implantation of a lens consisting of a biocompatible collagen copolymer (Visian implantable Collamer lens [ICL]; STAAR Surgical, Nidau, Switzerland) for moderate to high myopia. We evaluated 56 eyes of 34 patients with myopic refractive errors of -4.00 to -15.25 diopters (D) who underwent ICL implantation and routine postoperative examinations. Before and 1, 3, and 6 months and 1, 2, and 4 years after surgery, we assessed the safety, efficacy, predictability, stability, and adverse events of the surgery. Mean (SD) logMAR uncorrected and best spectacle-corrected visual acuities were -0.03 (0.23) and -0.21 (0.09), respectively, at 4 years after surgery. The mean (SD) safety and efficacy indexes were 1.19 (0.25) and 0.83 (0.29), respectively. At 4 years, 44 (79%) and 52 (93%) of the eyes were within +/-0.5 and +/-1.0 D, respectively, of the targeted correction. Mean (SD) manifest refraction changes of -0.24 (0.57) D occurred from 1 month to 4 years after surgery. No vision-threatening complications occurred during the observation period. Implantation of ICLs is safe and effective and provides predictable and stable refractive results in the treatment of moderate to high myopia during a 4-year observation period, suggesting its viability as a surgical option for the treatment of such eyes.

To compare the postoperative biomechanical properties of the cornea after photorefractive keratectomy (PRK) and after laser in situ keratomileusis (LASIK) in eyes with myopia. We retrospectively examined 27 eyes of 16 patients undergoing PRK and 31 eyes of 16 patients undergoing LASIK for the correction of myopia. Corneal hysteresis (CH) and corneal resistance factor (CRF) were measured with Ocular Response Analyzer before and 3 months after surgery. We also investigated the relationship between these biomechanical changes and the amount of myopic correction. The CH was decreased significantly from 10.8 +/- 1.3 (mean +/- SD) mmHg to 9.2 +/- 1.6 mmHg after PRK (P < 0.001), and from 10.8 +/- 1.4 mmHg to 8.6 +/- 0.9 mmHg after LASIK (P < 0.001). The CRF was also decreased significantly, from 10.3 +/- 1.5 mmHg to 8.4 +/- 1.8 mmHg after PRK (P < 0.001), and from 10.3 +/- 1.5 mmHg to 7.7 +/- 1.3 mmHg after LASIK (P < 0.001). The amount of decrease in CH and CRF was significantly larger after LASIK than after PRK (P = 0.04). There was a significant correlation between the amount of myopic correction and changes in biomechanical properties after PRK (r = -0.61, P < 0.01 for CH, r = -0.41, P < 0.05 for CRF) and LASIK (r = -0.37, P < 0.05 for CH, r = -0.45, P < 0.05 for CRF). Both PRK and LASIK can affect the biomechanical strength of the cornea depending on the amount of myopic correction. The amount of biomechanical changes is larger after LASIK than after PRK. From a biomechanical viewpoint, PRK may be a less invasive surgical approach for the correction of myopia than LASIK.